2nd IOEMLA Workshop: Accepted Papers and Information

Welcome Message from IOEMLA-2019 International Workshop Co-chair

Welcome to the 2nd International Workshop on Internet of Everything and Machine Learning Applications (IOEMLA-2019), which will be held in conjunction with the 33rd International Conference on Advanced Information Networking and Applications (AINA-2019) at Kunibiki Messe, Matsue, Japan, from March 27–29, 2019. The workshop is intended to facilitate exchange of ideas between researchers and presents the latest developments and research in the areas of IoE and machine learning in cross-disciplinary domains such as data science, IoT, industrial IoE, and computer and intelligent networks.
This international workshop collected research papers written by some established international researchers. These papers went through multiple review cycles and were handpicked based on their quality, clarity, and relevance to the theme of this workshop.
Many people have kindly helped us to prepare and organize the IOEMLA-2019 workshop. Firstly, I would like to thank the authors who submitted high-quality papers. I also would like to acknowledge the valuable comments of the Reviewers, which have enabled us to select these papers out of the so many submissions we received.
I would like to give our special thanks to Prof. Leonard Barolli and Prof. Makoto Takizawa, as Steering Committee Co-chairs of AINA International Conference, for their strong encouragement and guidance to organize the workshop. I also would like to thank AINA-2019 General Co-chairs, PC Co-chairs, and Workshop Co-chairs for their continuous support throughout the entire process of the IOEMLA-2019 workshop. I do hope that you will have a wonderful time in Matsue, Japan.
Omid Ameri Sianaki
IOEMLA-2019 Workshop Co-chair

IOEMLA-2019 Organizing Committee

Workshop Co-chair

Omid Ameri Sianaki, Victoria University, Australia

Program Committee Members:

  • Elizabeth Chang, UNSW Canberra, Australia
  • Vidyasagar Potdar, Curtin University, Australia
  • Mahmoud El Khodr, CQUniversity, Australia
  • Ahmed Dawoud, Victoria University, Australia
  • Nedal Ababneh, Victoria University, Australia
  • Khaled Kourouche, Victoria University, Australia
  • Atif Ali, Victoria University, Australia
  • Shafquat Hussain, Victoria University, Australia
  • Mehregan Mahdavi, Victoria University, Australia
  • Morteza Saberi UNSW, Canberra, Australia
  • Thomas Houghton, Curtin University, Australia
  • Yuan Miao, Victoria University, Australia
  • Jakub Szajman, Victoria University, Australia
  • Zoohan Gani, Victoria University, Australia
  • Gitesh Raikundalia, Victoria University, Australia
  • Javid Taheri, Karlstad University, Sweden
  • Artemis Gharagozlu, Victoria University, Australia
  • Khandakar Ahmed, Victoria University, Australia
  • Farshid Hajati, Victoria University, Australia
  • Azadeh Rajabian Tabesh, Victoria University, Australia
  • Pantea Aria, La Trobe University, Australia
  • Ashkan Yusefi UC Berkeley, USA
  • Ali Anaissi The University of Sydney, Australia
  • Mohammadreza Hoseinfarahabady, The University of Sydney, Australia
  • Israel Casas Lopez, Victoria University, Australia
  • Belal Alsinglawi, Western Sydney University, Australia

1Social Credibility Incorporating
Semantic Analysis and Machine Learning:
A Survey of the State-of-the-Art and Future
Research Directions

Bilal Abu-Salih(&), Bushra Bremie, Pornpit Wongthongtham,
Kevin Duan, Tomayess Issa, Kit Yan Chan,
Mohammad Alhabashneh, Teshreen Albtoush,
Sulaiman Alqahtani, Abdullah Alqahtani, Muteeb Alahmari,
Naser Alshareef, and Abdulaziz Albahlal

The wealth of Social Big Data (SBD) represents a unique opportunity
for organisations to obtain the excessive use of such data abundance to
increase their revenues. Hence, there is an imperative need to capture, load,
store, process, analyse, transform, interpret, and visualise such manifold social
datasets to develop meaningful insights that are specific to an application’s
domain. This paper lays the theoretical background by introducing the state-of the art literature review of the research topic. This is associated with a critical
evaluation of the current approaches, and fortified with certain recommendations indicated to bridge the research gap.

2Source Codes Classification Using a Modified
Instruction Count Pass

Omar Darwish, Majdi Maabreh, Ola Karajeh,
and Belal Alsinglawi

The vulnerability is a flaw in the system’s implementation which
may result in severe consequences. The existence of these flaws should be
detected and managed. There are several types of research which provide different solutions to detect these flaws through static analysis of the original
source codes. Static analysis process has many disadvantages, some of them are;
slower than compilation and produce high false positive rate. In this project, we
introduce a prediction technique using the output of one of the LLVM passes;
“InstCount”. A classifier was built based on the output of this pass on 500
source codes written in C and C++ languages with 88% of accuracy. A comparison between our classifier and Clang static analyzer showed that the classifier super performed to predict the existence of memory leak and Null pointers.
The experiment also showed that this classifier could be applied or integrated
with static analysis tools for more efficient results.

3Predictive Analytics and Deep Learning
Techniques in Electronic Medical Records:
Recent Advancements and Future Direction

Belal Alsinglawi and Omar Mubin

Western Sydney University, Parramatta, Sydney, NSW, Australia

The demands on medical services are increasing rapidly in the global
context. Therefore, handling beds availability, identifying and managing the
length of stay (LOS) is creating persistent needs for the physicians, nurses,
clinicians, hospital management, and caregivers in the public hospital admissions and the private hospital admissions. Health analytics provides unprecedented ways to predict trends, patients’ future outcomes, knowledge discovery, and improving the decision making in the clinical settings.

This paper reviews the state-of-the-art machine learning, deep learning techniques and the related work in relation to the length of stay common hospital admissions. Research trends and future direction for the forecasting LOS in medical admissions are
discussed in this paper.

4- Big Data Analytics for Electricity Price
Forecast

Ashkan Yousefi, Omid Ameri Sianaki, and Tony Jan (2)

Victoria University Sydney, Sydney, Australia

2.Melbourne Institute of Technology, Melbourne, Australia

Electricity Price forecast is a major task in smart grid operation.
There is a massive amount of data flowing in the power system including the
data collection by control systems, sensors, etc. In addition, there are many data
points which are not captured and processed by the energy market operators and
electricity network operators including gross domestic product, the price of fuel,
government policy and incentives for renewable and green energy sectors as
well as impacts on new technologies such as battery technology advancement
and electric vehicles. In this study, data points from 2001 to 2017 were collected
and 78 data points are considered for analyses to select the highly-correlated
features which could potentially affect the electricity price. In the first step, a
comprehensive correlation method using Pearson Correlation Coefficient is
applied to find the points which are correlated with the electricity price. In the
next step, the correlated data is fed to the machine learning algorithm for price
forecast. The algorithm results were tested in the historical data in California and
the outcomes were satisfactory for the three years forecast. The combination of
featured selection and machine learning is giving superior outcomes than the
traditional methods.

5-Queue Formation Augmented with Particle
Swarm Optimisation to Improve Waiting Time
in Airport Security Screeni

Mohamad Naji, Ahmed Al-Ani, Ali Braytee, Ali Anaissi,
and Paul Kennedy

Airport security screening processes are essential to ensure the safety
of both passengers and the aviation industry. Security at airports has improved
noticeably in recent years through the utilisation of state-of-the-art technologies
and highly trained security officers. However, maintaining a high level of
security can be costly to operate and implement. It may also lead to delays for
passengers and airlines. This paper proposes a novel queue formation method
based on a queueing theory model augmented with a particle swarm optimisation method known as QQT-PSO to improve the average waiting time in airport security areas. Extensive experiments were conducted using real-world data sets collected from Sydney airport. Compared to the existing system, our method significantly reduces the average waiting time and operating cost by 11.89% compared to the one-queue formation.

6-Polar Topographic Derivatives for 3D
Face Recognition: Application to Internet
of Things Securit
y

Farshid Hajati1, Ali Cheraghian, Omid Ameri Sianaki, Behnam Zeinali, and Soheila Gheisari

We propose Polar Topographic Derivatives (PTD) to fuse the
shape and texture information of a facial surface for 3D face recognition.
Polar Average Absolute Deviations (PAADs) of the Gabor topography
maps are extracted as features. High-order polar derivative patterns are
obtained by encoding texture variations in a polar neighborhood. By
using the and Bosphorus 3D face database, our method shows that it is
robust to expression and pose variations comparing to existing state-ofthe-
art benchmark approaches.

7-A Survey on Conversational Agents/Chatbots
Classification and Design Techniques

Shafquat Hussain, Omid Ameri Sianaki, and Nedal Ababneh

A chatbot can be defined as a computer program, designed to interact
with users using natural language or text in a way that the user thinks he is
having dialogue with a human. Most of the chatbots utilise the algorithms of
artificial intelligence (AI) in order to generate required response. Earlier chatbots merely created an illusion of intelligence by employing much simpler pattern matching and string processing design techniques for their interaction with users using rule-based and generative-based models. However, with the emergence of new technologies more intelligent systems have emerged using complex knowledge-based models. This paper aims to discuss chatbots classification, their design techniques used in earlier and modern chatbots and how the two main categories of chatbots handle conversation context.

8- Dimensionality Reduction for Network
Anomalies Detection: A Deep Learning Approach

Ahmed Dawoud, Seyed Shahristani, and Chun Raun

Cyber threats are a severed challenge in current communications
networks. Several security measures were introduced to at different network
layers to enhance security. One of the common networking security solutions is
intrusion detection and prevention systems, with more focus on detecting the
attacks. Various approaches are being used in network threat detection, for
instance, signature-based and anomalies detection methods. Signature-based
depends on a database of predefined attacks signature, in operation, the systems
compare the traffic against the signature, if a match occurs, then an attack is
identified. This approach cannot detect attacks that do not have a signature in the database. The anomalies detection approach utilizing various approaches to
define the threats, for instance, statistical, and machine learning algorithms.
Several machine learning algorithms had been used for network anomalies
detection. A major common deficiency was poor accuracy, which kept the
approach not industrially applicable. In this paper, we propose a framework for
network anomalies detection. The proposed framework showed improvement in detection accuracy. The framework adopts semi-unsupervised algorithms for
novelty detection to tackle the rapid development in the cyber security attacks.
The framework embraces the unsupervised deep learning in more elegant
technique, where it dramatically reduces the features from the first phase

9-Blockchain: A Research Framework for Data
Security and Privacy

Farhad Daneshgar, Omid Ameri Sianaki,
and Prabhat Guruwacharya

As an emerging field of research, Blockchain is currently experiencing
a lack of research frameworks to guide studies in the field. Emerging
technologies are usually triggered first, and then the academic world will attempt to develop discipline for these technologies. Our current exploratory work-in progress is an initial attempt in developing a research framework for investigating the security of data through Blockchain. This study is the first phase of more extensive study that aims to provide a conceptual framework for blockchain research in general. In its current form, the initial proposed framework of this study can be used for both scoping as well as evaluating existing research approaches in the field of data security through blockchain technology. It is also expected to facilitate scoping and categorizing future studies by providing a set of defined set research categories in the field.

10-Environmental Monitoring Intelligent System
Using Wireless Nanosensor Networks

Nedal Ababneh, Omid Ameri Sianaki, and Shafquat Hussain

Wireless nanosensor networks are envisioned to operate in the THz
band, due to the small size of the network devices. The tiny dimensions of the
nanosensor devices allow them to be embedded in various objects and devices in our environment to obtain fine-grained data, such as object’s components or its internal status, from hard-to-reach locations in a non-invasive way, and to
perform additional in-network processing and thereby enabling a myriad of
novel applications in industrial, biomedical, and agricultural settings that cannot be realized with conventional sensor networks.

In this work, we propose a crop monitoring/defense application of nanosensors, for detection of any compound
released by plants. Based on the detected volatile compounds, the state of the
plant in its surrounding can be recognized and chemical nanosensors can release the same natural composites to reinforce the plants defense mechanism in case of insect attack. Our approach centers around the creation of a wireless
nanosensor network (WNSN) wherein large number of chemical nanosensor
devices, which is connected to a remote center via the Internet to provide remote monitoring/controlling capabilities.